Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach

01/16/2023
by   Yassir Bendou, et al.
0

The field of visual few-shot classification aims at transferring the state-of-the-art performance of deep learning visual systems onto tasks where only a very limited number of training samples are available. The main solution consists in training a feature extractor using a large and diverse dataset to be applied to the considered few-shot task. Thanks to the encoded priors in the feature extractors, classification tasks with as little as one example (or "shot”) for each class can be solved with high accuracy, even when the shots display individual features not representative of their classes. Yet, the problem becomes more complicated when some of the given shots display multiple objects. In this paper, we present a strategy which aims at detecting the presence of multiple and previously unseen objects in a given shot. This methodology is based on identifying the corners of a simplex in a high dimensional space. We introduce an optimization routine and showcase its ability to successfully detect multiple (previously unseen) objects in raw images. Then, we introduce a downstream classifier meant to exploit the presence of multiple objects to improve the performance of few-shot classification, in the case of extreme settings where only one shot is given for its class. Using standard benchmarks of the field, we show the ability of the proposed method to slightly, yet statistically significantly, improve accuracy in these settings.

READ FULL TEXT

page 1

page 2

page 4

research
10/18/2021

Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning

Few-shot classification is a challenging problem due to the uncertainty ...
research
08/22/2020

Few-Shot Learning with Intra-Class Knowledge Transfer

We consider the few-shot classification task with an unbalanced dataset,...
research
06/05/2019

Discriminative Few-Shot Learning Based on Directional Statistics

Metric-based few-shot learning methods try to overcome the difficulty du...
research
08/23/2021

Graph-LDA: Graph Structure Priors to Improve the Accuracy in Few-Shot Classification

It is very common to face classification problems where the number of av...
research
01/12/2021

Improving Classification Accuracy with Graph Filtering

In machine learning, classifiers are typically susceptible to noise in t...
research
09/23/2020

Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning

Deep learning has shown great success in settings with massive amounts o...
research
01/24/2022

EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients

Few-shot learning aims at leveraging knowledge learned by one or more de...

Please sign up or login with your details

Forgot password? Click here to reset